# Parallel Hierarchical Transformer with Attention Alignment for Abstractive Multi-Document Summarization

arXiv: https://arxiv.org/abs/2208.07845 · HTML: https://mlsanity.com/paper/2208.07845/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 38 references that are in the map.
- First posted on arXiv 16 Aug 2022.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents](https://mlsanity.com/paper/1804.05685/) (2018)
- [Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model](https://mlsanity.com/paper/1906.01749/) (2019)
- [A Neural Attention Model for Abstractive Sentence Summarization](https://mlsanity.com/paper/1509.00685/) (2015)
- [Generating Wikipedia by Summarizing Long Sequences](https://mlsanity.com/paper/1801.10198/) (2018)
- [Bottom-Up Abstractive Summarization](https://mlsanity.com/paper/1808.10792/) (2018)
- [Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting](https://mlsanity.com/paper/1805.11080/) (2018)
- [Hierarchical Transformers for Multi-Document Summarization](https://mlsanity.com/paper/1905.13164/) (2019)
- [HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization](https://mlsanity.com/paper/1905.06566/) (2019)
- [Multi-Reward Reinforced Summarization with Saliency and Entailment](https://mlsanity.com/paper/1804.06451/) (2018)
- [Leveraging Graph to Improve Abstractive Multi-Document Summarization](https://mlsanity.com/paper/2005.10043/) (2020)
- [Multi-document Summarization via Deep Learning Techniques: A Survey](https://mlsanity.com/paper/2011.04843/) (2020)
- [Adapting the Neural Encoder-Decoder Framework from Single to Multi-Document Summarization](https://mlsanity.com/paper/1808.06218/) (2018)
- [What to talk about and how? Selective Generation using LSTMs with Coarse-to-Fine Alignment](https://mlsanity.com/paper/1509.00838/) (2015)
- [Sentence-Level Content Planning and Style Specification for Neural Text Generation](https://mlsanity.com/paper/1909.00734/) (2019)

## Abstract (arXiv)

In comparison to single-document summarization, abstractive Multi-Document Summarization (MDS) brings challenges on the representation and coverage of its lengthy and linked sources. This study develops a Parallel Hierarchical Transformer (PHT) with attention alignment for MDS. By incorporating word- and paragraph-level multi-head attentions, the hierarchical architecture of PHT allows better processing of dependencies at both token and document levels. To guide the decoding towards a better coverage of the source documents, the attention-alignment mechanism is then introduced to calibrate beam search with predicted optimal attention distributions. Based on the WikiSum data, a comprehensive evaluation is conducted to test improvements on MDS by the proposed architecture. By better handling the inner- and cross-document information, results in both ROUGE and human evaluation suggest that our hierarchical model generates summaries of higher quality relative to other Transformer-based baselines at relatively low computational cost.